Abstract
Abstract
Sucker Rod Pumps (SRPs) are the leading Artificial Lift System (ALS) worldwide for low oil-producing wells. Yet, SRPs have been overlooked in the ongoing wave of digitalization within oil and gas production. SRP operation and optimization processes are outdated and still based on simple field legacy ‘rule of thumb’ practices. This paper presents a simple yet innovative solution that uses an Industrial Internet of Things (IIoT) framework to autonomously optimize SRP production while minimizing pump shutdowns.
The SRP optimization algorithm, rule-based in nature, gathers trending operational data from the controller via a time-moving window. This time window represents a well snapshot that is used to evaluate performance indicators at different operating pump frequencies. These calculated performance indicators, namely Production Indicator (PI), Combined Indicators (CI) and Combined Indicator-Quadratic Penalty (CI-QP), are mainly a function of pump fillage, strokes per minute, and well shutdowns. The PI prioritizes higher well production, while the CI and CI-QP penalizes shutdowns to reduce pump failure rates. The algorithm dynamically evaluates the well performance indicators to recommend and implement an optimal frequency setpoint to the pump controller. This solution has been dockerized and developed as an Edge Application, capable of running directly on-site in an IIoT Gateway device. This application has been tested on eight SRP wells for several months with excellent results. These wells were tested in both PI and CI modes. As a result, inferred production increased by 15% and shutdowns reduced by 29% in average, in all tested wells. The solution provides an easy yet powerful tool that can be scaled to manage multiple wells by providing optimal setpoints based on pump-specific conditions. Additionally, features like user-configurable optimization cycle duration can be included for faster well optimization.
With the advent of the digital oilfield, the solution evaluates trending data by leveraging IIoT to optimize SRP operation using real-time performance indicators of well production and shutdowns. This completely autonomous, edge-based solution requires no manual intervention and can be scaled to hundreds of wells.